© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64469
    Prev
    Next
    INDEX
    Explanations

    derived

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     headings
    -0.26
    lig
    -0.25
     NSInteger
    -0.25
    çݰ代
    -0.25
    assium
    -0.24
    åĨĽäºº
    -0.24
    ition
    -0.23
    itionally
    -0.23
    çı¾ä»£
    -0.23
    ARS
    -0.23
    POSITIVE LOGITS
    åѵåĮĸ
    0.25
    å¢ŀè¿Ľ
    0.25
    交
    0.24
     embr
    0.24
    flow
    0.24
    ä¸ĭ游
    0.23
    _UT
    0.23
     prune
    0.23
    交èŀį
    0.23
    prit
    0.23
    Activations Density 18.110%

    No Known Activations